{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:58Z","timestamp":1775199958602,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100013177","name":"Interior Business Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013177","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434701","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion"],"prefix":"10.1109","author":[{"given":"Yu","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,Computer Science,Hangzhou,China"}]},{"given":"Baotong","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Rochester,Electrical and Computer Engineering,Rochester,USA"}]},{"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Rochester,Electrical and Computer Engineering,Rochester,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.396"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref3","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. International Conference on Machine Learning (ICML).","author":"Qian"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1788"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10277"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.687"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-319"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832303"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414487"},{"key":"ref15","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Choi","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3308474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747558"},{"key":"ref18","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ren"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413973"},{"key":"ref20","article-title":"Fasts2s-vc: Streaming non-autoregressive sequence-to-sequence voice conversion","author":"Kameoka","year":"2021","journal-title":"arXiv preprint arXiv:2104.06900"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096066"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446229"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-836"},{"key":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-441"},{"key":"ref28","article-title":"Daft-exprt: Robust prosody transfer across speakers for expressive speech synthesis","volume-title":"arXiv preprint arXiv:2108.02271","author":"Zardi","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0797"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-838"},{"key":"ref31","article-title":"Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang"},{"key":"ref32","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Ju"},{"key":"ref33","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2407.05407"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.117"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.13"},{"key":"ref38","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29932"},{"key":"ref40","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00003","article-title":"Deconvolution and checkerboard artifacts","author":"Odena","year":"2016","journal-title":"Distill"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0034"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0707"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref48","article-title":"Quickvc: Any-to-many voice conversion using inverse short-time fourier transform for faster conversion","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv:2302.08296"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434701.pdf?arnumber=11434701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:31Z","timestamp":1775192311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434701","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}